Speed regulator auxiliary decision-making method and system based on power plant speed regulator digital mapping model

Abstract

The invention provides a speed regulator auxiliary decision-making method and system based on a digital mapping model of a power plant speed regulator. The method comprises the following steps: determining whether to start judgment of first load shedding or not based on load values at a plurality of time points; if the judgment of the first load shedding is started, extracting a judgment time period of the first load shedding, comparing the judgment time period with a preset scheduling time period, and judging whether the judgment of the second load shedding is started or not; if the second load shedding judgment is started, determining the fluctuation trend of the power grid frequency or the power generator rotating speed in a judgment time period based on the historical data of the power grid frequency or the power generator rotating speed, and comparing the fluctuation trend of the power grid frequency or the power generator rotating speed with the load change trend in the judgment time period based on a preset digital mapping model, judging whether a load shedding condition occurs or not; and the load shedding condition is fed back to a control end, so that the control end adjusts control parameters of the speed regulator based on the load shedding condition.

Description

Technical Field

[0001] The present invention relates to the field of power plant control technology, and in particular to a speed governor auxiliary decision method and system based on a power plant speed governor digital mapping model. Background Art

[0002] Load shedding in turbine power generation refers to a phenomenon in which the load on the turbine generator set suddenly decreases significantly or completely loses its load due to some reason during its operation, resulting in a rapid increase in the speed of the unit and unstable voltage and current. This phenomenon usually occurs in the event of a power grid failure, a sudden change in user load, or a turbine failure.

[0003] Specifically, when the hydro-turbine generator set operates normally, it will adjust its own power generation according to the load demand of the power grid and maintain a stable operating state. However, when the power grid fails or the user load suddenly decreases, the load carried by the unit will decrease rapidly, causing the speed of the turbine rotor to increase rapidly. Due to the increase in speed, the dynamic stability of the unit will be affected, and the voltage and current will become unstable, which may cause the turbine to dump load. The hazards of turbine load dump are multifaceted. First, the rapid increase in speed will increase the centrifugal force of the rotating parts of the unit, resulting in increased vibration and swing of the unit, and may even cause collision and damage inside the unit. Secondly, the negative water hammer effect generated during the load dump process will damage components such as the turbine runner and the turbine top cover. In addition, load dumping may also cause the generator terminal voltage to increase, threatening the insulation of the generator's stator winding.

[0004] In order to deal with the load shedding of turbine power generation, a speed governor is usually required to perform corresponding regulation, but the existing speed governors often react slowly and are difficult to respond in time.

[0005] In view of this, the present invention is proposed. Summary of the invention

[0006] The purpose of the present invention is to provide a speed governor auxiliary decision-making method and system based on a power plant speed governor digital mapping model. This scheme compares the load change with the fluctuation trend of the grid frequency and the generator speed to accurately determine the load shedding situation.

[0007] The present invention provides a speed governor auxiliary decision method based on a power plant speed governor digital mapping model, the method comprising the following steps:

[0008] Acquire the load value of the generator set in real time, and determine whether to start the first load shedding based on the load values ​​at multiple time points;

[0009] If it is determined that the first load shedding determination is to be started, extracting the first load shedding determination time period, comparing the determination time period with the preset scheduling time period, and determining whether to start the second load shedding determination;

[0010] If the second load shedding determination is started, historical data of the grid frequency or the generator speed is extracted from the database based on the determination time period;

[0011] Determine the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed, and compare the fluctuation trend of the grid frequency or the generator speed with the load change trend in the determination time period based on a preset digital mapping model to determine whether load shedding occurs;

[0012] The load shedding condition is fed back to the control end so that the control end adjusts the speed regulator control parameters based on the load shedding condition.

[0013] The above scheme is adopted. This scheme first determines the time period when the load changes. Since some load changes are caused by normal load scheduling or changes in grid demand, this scheme matches the time periods of the two through the first load shedding determination process, excludes normal load scheduling or grid demand changes, and ensures the accuracy of the determination. Since the load shedding process will cause synchronous fluctuations in the grid frequency or generator speed, this scheme further compares the load changes with the fluctuation trends of the grid frequency and the generator speed to accurately determine the load shedding situation.

[0014] In some embodiments of the present invention, in the step of obtaining the load value of the generator set in real time and determining whether to start the first load shedding based on the load values ​​at multiple time points:

[0015] Every two adjacent time points are regarded as a time point pair for determination;

[0016] For each time point pair, the fluctuation amplitude is calculated based on the previous time point and the first preset number of time points before the time point and the next time point and the first preset number of time points after the time point in the time point pair;

[0017] Whether to start the first load shedding is determined based on the fluctuation amplitude.

[0018] In some embodiments of the present invention, in the step of calculating the fluctuation amplitude for each time point pair based on the previous time point and a first preset number of time points before the time point and the next time point and a first preset number of time points after the time point in the time point pair, the average value of the load value of the previous time point in the time point pair and the first preset number of time points before the time point is calculated, and the average value of the load value of the next time point in the time point pair and the first preset number of time points after the time point is calculated, and the difference between the two average values ​​is calculated as the fluctuation amplitude.

[0019] By adopting the above scheme, in the judgment process of this scheme, through the setting of time point pairs, every two time points can be used as the dividing points of the fluctuation to judge each time point pair one by one, so as to ensure the refinement of the judgment; and in the specific fluctuation amplitude calculation process, the first preset number of time points before and after the time point pair are included in the calculation to accurately calculate the value of the fluctuation amplitude.

[0020] In some embodiments of the present invention, in the step of calculating the difference between two average values ​​as the fluctuation amplitude, if the difference between the average value of the load value of the previous time point in the time point pair and the first preset number of time points before the time point and the average value of the load value of the next time point in the time point pair and the first preset number of time points after the time point is negative, it is determined that no load shedding occurs within the determination time period corresponding to the time point, and the determination of the next time point pair is continued.

[0021] In the specific implementation process, if the difference between the two average values ​​is a negative number, it means that the load has increased. The positive load growth is contrary to the load shedding situation. Therefore, it is determined that the load shedding situation has not occurred.

[0022] In some embodiments of the present invention, in the step of extracting the first load shedding determination time period, comparing the determination time period with a preset scheduling time period, and determining whether to start the second load shedding determination:

[0023] constructing a second preset number of time points before and after the second preset number of time points of the time point pair determined as corresponding to the start of the first load shedding as a determination time period;

[0024] The overlapping time period between the determination time period and the scheduling time period is calculated, and whether to start the second load shedding determination is determined based on the ratio of the overlapping time period to the determination time period.

[0025] In some embodiments of the present invention, in the step of calculating the overlapping time period between the determination time period and the scheduling time period, and determining whether to start the second load shedding based on the ratio of the overlapping time period to the determination time period:

[0026] Calculating a ratio of the number of time points in the overlap time period to the number of time points in the determination time period as a ratio of the overlap time period to the determination time period;

[0027] If the value of the ratio is less than a preset ratio threshold, the second load rejection determination is started;

[0028] If the value of the ratio is not less than a preset ratio threshold, it is determined that the load value fluctuation in the determination time period is a normal fluctuation, and the determination of the second load shedding is not started.

[0029] With the above scheme, since normal load scheduling or changes in grid demand may also cause load attenuation, this scheme compares the scheduling time period corresponding to normal changes with the judgment time period to determine the overlap between the two, and then determines whether the load change within the judgment time period is caused by normal changes, thereby excluding normal fluctuations and improving the judgment accuracy.

[0030] In some embodiments of the present invention, in the step of determining the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed:

[0031] Constructing a line graph based on the grid frequency and the generator speed at each time point in the determination time period;

[0032] Based on the slope of the line between every two adjacent time points in the line graph corresponding to the grid frequency and the generator speed, a first fluctuation trend vector and a second fluctuation trend vector are respectively constructed.

[0033] Using the above scheme, since the reduction of load during load shedding will cause synchronous fluctuations in the grid frequency and the engine speed, this scheme constructs a first fluctuation trend vector and a second fluctuation trend vector based on the grid frequency and the generator speed, respectively, to facilitate the subsequent combination of the above two characteristics to determine whether a load shedding situation occurs.

[0034] In some embodiments of the present invention, the step of determining the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed further includes:

[0035] Calculate a third fluctuation trend vector symmetrical to the second fluctuation trend vector based on the second fluctuation trend vector;

[0036] A total fluctuation trend vector is calculated based on the first fluctuation trend vector and the third fluctuation trend vector, and the total fluctuation trend vector is used as the fluctuation trend of the determination time period.

[0037] In some embodiments of the present invention, in the step of calculating a third fluctuation trend vector symmetrical to the second fluctuation trend vector based on the second fluctuation trend vector, the opposite number of the value of each dimension in the second fluctuation trend vector is calculated and used as the value of the corresponding dimension in the third fluctuation trend vector.

[0038] Using the above scheme, the second fluctuation trend vector corresponds to the change in the engine speed, and the reduction in load will cause the engine speed to increase, and the changes in the two are inversely proportional. Therefore, this scheme calculates a symmetrical third fluctuation trend vector based on the second fluctuation trend vector to ensure the consistency of the changes in the first fluctuation trend vector, the third fluctuation trend vector and the load change trend, which facilitates the subsequent trend coincidence judgment.

[0039] In some embodiments of the present invention, in the step of comparing the fluctuation trend of the grid frequency or the generator speed with the load change trend in the determination time period based on a preset digital mapping model to determine whether a load shedding situation occurs:

[0040] Constructing a line graph based on the load value at each time point in the determination time period, and constructing a load change vector based on the slope of the line connecting every two adjacent time points in the line graph;

[0041] The total fluctuation trend vector and the load change vector corresponding to the fluctuation trend of the determination time period are input into the pre-trained digital mapping model to obtain the trend coincidence degree;

[0042] Whether a load shedding situation occurs is determined based on the trend coincidence.

[0043] In some embodiments of the present invention, in the step of determining whether a load shedding situation occurs based on the trend coincidence, if the trend coincidence is greater than a preset coincidence threshold, it is determined that a load shedding situation occurs.

[0044] Using the above scheme, since the reduction of load during load shedding will cause synchronous fluctuations in the grid frequency and the engine speed, this scheme calculates the fluctuation consistency of the three through a pre-trained neural network model, and determines whether load shedding occurs based on the degree of consistency.

[0045] On the other hand, the present invention also relates to a speed governor auxiliary decision-making system based on a digital mapping model of a power plant speed governor, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0046] In summary, the present invention has the following beneficial effects:

[0047] 1. This scheme first determines the time period when the load changes. Since some load changes are caused by normal load scheduling or changes in grid demand, this scheme matches the time periods of the two through the first load shedding determination process, excludes normal load scheduling or grid demand changes, and ensures the accuracy of the determination. Since the load shedding process will cause synchronous fluctuations in the grid frequency or generator speed, this scheme further compares the load changes with the fluctuation trends of the grid frequency and generator speed to accurately determine the load shedding situation.

[0048] 2. In the determination process of this scheme, by setting the time point pair, every two time points can be used as the demarcation point of the fluctuation to determine the time point pair one by one, so as to ensure the refinement of the determination; and in the specific fluctuation amplitude calculation process, the first preset number of time points before and after the time point pair are included in the calculation to accurately calculate the value of the fluctuation amplitude;

[0049] 3. Since normal load dispatching or changes in grid demand may also cause load attenuation, this solution compares the dispatching time period corresponding to normal changes with the determination time period to determine the overlap between the two, and then determines whether the load change within the determination time period is caused by normal changes, thereby excluding normal fluctuations and improving the determination accuracy;

[0050] 4. In this solution, the second fluctuation trend vector corresponds to the change of the engine speed, and the reduction of load will lead to the increase of engine speed, and the changes of the two are inversely proportional. Therefore, this solution calculates a symmetrical third fluctuation trend vector based on the second fluctuation trend vector to ensure the consistency of the first fluctuation trend vector, the third fluctuation trend vector and the load change trend, which is convenient for subsequent trend coincidence judgment;

[0051] 5. Since the reduction of load during load shedding will cause synchronous fluctuations in the grid frequency and engine speed, this solution calculates the fluctuation consistency of the three through a pre-trained neural network model, and determines whether load shedding occurs based on the degree of consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 It is a schematic diagram of an implementation method of a speed governor auxiliary decision-making method based on a power plant speed governor digital mapping model of the present invention;

[0054] Figure 2for Figure 1 Schematic diagram of the step expansion processing of step S400 in FIG. DETAILED DESCRIPTION

[0055] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0056] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0057] like Figure 1 As shown, the present invention provides a speed governor auxiliary decision method based on a power plant speed governor digital mapping model, the method comprising the steps of:

[0058] Step S100, obtaining the load value of the generator set in real time, and determining whether to start the first load shedding based on the load values ​​at multiple time points;

[0059] In the specific implementation process, the load value of the generator set can be obtained by using a direct monitoring method or an indirect monitoring method;

[0060] If the direct detection method is adopted, a load sensor can be installed at the output end of the generator set to measure the output power or current of the generator set in real time, thereby indirectly obtaining the load situation; the load sensor can accurately convert the load into an electrical signal for the governor to read and analyze;

[0061] If the indirect monitoring method is adopted, the real-time load data displayed on the control panel of the generator set can be obtained; the load information can be obtained through the communication interface with the generator control panel (such as RS-485, CAN bus, etc.).

[0062] Step S200, if it is determined to start the first load shedding determination, extract the first load shedding determination time period, compare the determination time period with the preset scheduling time period, and determine whether to start the second load shedding determination;

[0063] Step S300, if the second load shedding determination is started, historical data of the grid frequency or the generator speed is extracted from the database based on the determination time period;

[0064] In a specific implementation process, the historical data is obtained from a database of a power plant system, and specifically, is efficiently extracted from a cache file.

[0065] Step S400, determining the fluctuation trend of the grid frequency or the generator speed in a determination time period based on the historical data of the grid frequency or the generator speed, and comparing the fluctuation trend of the grid frequency or the generator speed with the load change trend in the determination time period based on a preset digital mapping model to determine whether a load shedding situation occurs;

[0066] In the specific implementation process, the digital mapping model is a pre-trained convolutional neural network model.

[0067] Step S500, feeding back the load shedding condition to the control end, so that the control end adjusts the speed regulator control parameters based on the load shedding condition.

[0068] In the specific implementation process, the load condition is the load change trend corresponding to the judgment time period. The control end can be the management end of the power plant. The power plant staff can manually adjust the working parameters of the speed regulator according to the specific load change trend, or set up automated adjustment software to automatically set the working parameters of the speed regulator based on the load change trend.

[0069] The above scheme is adopted. This scheme first determines the time period when the load changes. Since some load changes are caused by normal load scheduling or changes in grid demand, this scheme matches the time periods of the two through the first load shedding determination process, excludes normal load scheduling or grid demand changes, and ensures the accuracy of the determination. Since the load shedding process will cause synchronous fluctuations in the grid frequency or generator speed, this scheme further compares the load changes with the fluctuation trends of the grid frequency and the generator speed to accurately determine the load shedding situation.

[0070] In some embodiments of the present invention, in the step of obtaining the load value of the generator set in real time and determining whether to start the first load shedding based on the load values ​​at multiple time points:

[0071] Every two adjacent time points are regarded as a time point pair for determination;

[0072] For each time point pair, the fluctuation amplitude is calculated based on the previous time point and the first preset number of time points before the time point and the next time point and the first preset number of time points after the time point in the time point pair;

[0073] Whether to start the first load shedding is determined based on the fluctuation amplitude.

[0074] In some embodiments of the present invention, in the step of calculating the fluctuation amplitude for each time point pair based on the previous time point and a first preset number of time points before the time point and the next time point and a first preset number of time points after the time point in the time point pair, the average value of the load value of the previous time point in the time point pair and the first preset number of time points before the time point is calculated, and the average value of the load value of the next time point in the time point pair and the first preset number of time points after the time point is calculated, and the difference between the two average values ​​is calculated as the fluctuation amplitude.

[0075] By adopting the above scheme, in the judgment process of this scheme, through the setting of time point pairs, every two time points can be used as the dividing points of the fluctuation to judge each time point pair one by one, so as to ensure the refinement of the judgment; and in the specific fluctuation amplitude calculation process, the first preset number of time points before and after the time point pair are included in the calculation to accurately calculate the value of the fluctuation amplitude.

[0076] In some embodiments of the present invention, in the step of calculating the difference between two average values ​​as the fluctuation amplitude, if the difference between the average value of the load value of the previous time point in the time point pair and the first preset number of time points before the time point and the average value of the load value of the next time point in the time point pair and the first preset number of time points after the time point is negative, it is determined that no load shedding occurs within the determination time period corresponding to the time point, and the determination of the next time point pair is continued.

[0077] In the specific implementation process, if the difference between the two average values ​​is a negative number, it means that the load has increased. The positive load growth is contrary to the load shedding situation. Therefore, it is determined that the load shedding situation has not occurred.

[0078] In some embodiments of the present invention, in the step of extracting the first load shedding determination time period, comparing the determination time period with a preset scheduling time period, and determining whether to start the second load shedding determination:

[0079] constructing a second preset number of time points before and after the second preset number of time points of the time point pair determined as corresponding to the start of the first load shedding as a determination time period;

[0080] The overlapping time period between the determination time period and the scheduling time period is calculated, and whether to start the second load shedding determination is determined based on the ratio of the overlapping time period to the determination time period.

[0081] In some embodiments of the present invention, in the step of calculating the overlapping time period between the determination time period and the scheduling time period, and determining whether to start the second load shedding based on the ratio of the overlapping time period to the determination time period:

[0082] Calculating a ratio of the number of time points in the overlap time period to the number of time points in the determination time period as a ratio of the overlap time period to the determination time period;

[0083] If the value of the ratio is less than a preset ratio threshold, the second load rejection determination is started;

[0084] If the value of the ratio is not less than a preset ratio threshold, it is determined that the load value fluctuation in the determination time period is a normal fluctuation, and the determination of the second load shedding is not started.

[0085] With the above scheme, since normal load scheduling or changes in grid demand may also cause load attenuation, this scheme compares the scheduling time period corresponding to normal changes with the judgment time period to determine the overlap between the two, and then determines whether the load change within the judgment time period is caused by normal changes, thereby excluding normal fluctuations and improving the judgment accuracy.

[0086] like Figure 2 As shown, in some embodiments of the present invention, in the step of determining the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed:

[0087] Step S410, constructing a line graph based on the grid frequency and the generator speed at each time point in the determination time period;

[0088] In a specific implementation process, the line chart is constructed in a plane rectangular coordinate system, the horizontal axis of the coordinate system is the time point, and the vertical axis is the grid frequency or the generator speed.

[0089] Step S420, based on the slope of the line between every two adjacent time points in the line graph corresponding to the grid frequency and the generator speed, respectively construct a first fluctuation trend vector and a second fluctuation trend vector.

[0090] During the specific implementation process, the slope of the line between each two adjacent time points in the line graph corresponding to the grid frequency is used as the value of a dimension in the first fluctuation vector; the slope of the line between each two adjacent time points in the line graph corresponding to the generator speed is used as the value of a dimension in the second fluctuation vector.

[0091] Using the above scheme, since the reduction of load during load shedding will cause synchronous fluctuations in the grid frequency and the engine speed, this scheme constructs a first fluctuation trend vector and a second fluctuation trend vector based on the grid frequency and the generator speed, respectively, to facilitate the subsequent combination of the above two characteristics to determine whether a load shedding situation occurs.

[0092] In some embodiments of the present invention, the step of determining the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed further includes:

[0093] Step S430, calculating a third fluctuation trend vector symmetrical to the second fluctuation trend vector based on the second fluctuation trend vector;

[0094] Step S440, calculating a total fluctuation trend vector based on the first fluctuation trend vector and the third fluctuation trend vector, and using the total fluctuation trend vector as the fluctuation trend of the determination time period.

[0095] In some embodiments of the present invention, in the step of calculating a third fluctuation trend vector symmetrical to the second fluctuation trend vector based on the second fluctuation trend vector, the opposite number of the value of each dimension in the second fluctuation trend vector is calculated and used as the value of the corresponding dimension in the third fluctuation trend vector.

[0096] Using the above scheme, the second fluctuation trend vector corresponds to the change in the engine speed, and the reduction in load will cause the engine speed to increase, and the changes in the two are inversely proportional. Therefore, this scheme calculates a symmetrical third fluctuation trend vector based on the second fluctuation trend vector to ensure the consistency of the changes in the first fluctuation trend vector, the third fluctuation trend vector and the load change trend, which facilitates the subsequent trend coincidence judgment.

[0097] In some embodiments of the present invention, the step of comparing the fluctuation trend of the grid frequency or the generator speed with the load change trend in the determination time period based on a preset digital mapping model to determine whether a load shedding situation occurs includes:

[0098] Step S450, constructing a line graph based on the load value at each time point in the determination time period, and constructing a load change vector based on the slope of the line between every two adjacent time points in the line graph;

[0099] In the specific implementation process, the line graph in the step of constructing a line graph based on the load value at each time point in the determination time period is also set in a plane rectangular coordinate system, with the horizontal axis being the time point and the vertical axis being the load value.

[0100] Step S460, inputting the total fluctuation trend vector and the load change vector corresponding to the fluctuation trend of the determination time period into the pre-trained digital mapping model to obtain the trend coincidence degree;

[0101] Step S470: determining whether load shedding occurs based on the trend coincidence.

[0102] In some embodiments of the present invention, in the step of determining whether a load shedding situation occurs based on the trend coincidence, if the trend coincidence is greater than a preset coincidence threshold, it is determined that a load shedding situation occurs.

[0103] Using the above scheme, since the reduction of load during load shedding will cause synchronous fluctuations in the grid frequency and the engine speed, this scheme calculates the fluctuation consistency of the three through a pre-trained neural network model, and determines whether load shedding occurs based on the degree of consistency.

[0104] On the other hand, the present invention also relates to a speed governor auxiliary decision-making system based on a digital mapping model of a power plant speed governor, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0105] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the speed governor auxiliary decision method based on the digital mapping model of the power plant speed governor is implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0106] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0107] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0108] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0109] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A speed governor auxiliary decision method based on a power plant speed governor digital mapping model, characterized in that: The steps of the method include: Acquire the load value of the generator set in real time, and determine whether to start the first load shedding based on the load values ​​at multiple time points; If it is determined that the first load shedding determination is to be started, extracting the first load shedding determination time period, comparing the determination time period with the preset scheduling time period, and determining whether to start the second load shedding determination; If the second load shedding determination is started, historical data of the grid frequency or the generator speed is extracted from the database based on the determination time period; Determine the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed, and compare the fluctuation trend of the grid frequency or the generator speed with the load change trend in the determination time period based on a preset digital mapping model to determine whether load shedding occurs; The load shedding condition is fed back to the control end so that the control end adjusts the speed regulator control parameters based on the load shedding condition.

2. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 1 is characterized in that: In the step of obtaining the load value of the generator set in real time and determining whether to start the first load shedding based on the load values ​​at multiple time points: Every two adjacent time points are regarded as a time point pair for determination; For each time point pair, the fluctuation amplitude is calculated based on the previous time point and the first preset number of time points before the time point and the next time point and the first preset number of time points after the time point in the time point pair; Whether to start the first load shedding is determined based on the fluctuation amplitude.

3. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 2 is characterized in that: In the step of calculating the fluctuation amplitude for each time point pair based on the previous time point and the first preset number of time points before the time point and the next time point and the first preset number of time points after the time point in the time point pair, the average value of the load value of the previous time point and the first preset number of time points before the time point in the time point pair is calculated, and the average value of the load value of the next time point and the first preset number of time points after the time point in the time point pair is calculated, and the difference between the two average values ​​is calculated as the fluctuation amplitude.

4. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 2 is characterized in that: In the step of extracting the first load shedding determination time period, comparing the determination time period with a preset scheduling time period, and determining whether to start the second load shedding determination: constructing a second preset number of time points before and after the second preset number of time points of the time point pair determined as corresponding to the start of the first load shedding as a determination time period; The overlapping time period between the determination time period and the scheduling time period is calculated, and whether to start the second load shedding determination is determined based on the ratio of the overlapping time period to the determination time period.

5. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 4 is characterized in that: In the step of calculating the overlapping time period between the determination time period and the scheduling time period, and determining whether to start the second load shedding based on the ratio of the overlapping time period to the determination time period: Calculating a ratio of the number of time points in the overlap time period to the number of time points in the determination time period as a ratio of the overlap time period to the determination time period; If the value of the ratio is less than a preset ratio threshold, the second load rejection determination is started; If the value of the ratio is not less than a preset ratio threshold, it is determined that the load value fluctuation in the determination time period is a normal fluctuation, and the determination of the second load shedding is not started.

6. The speed governor auxiliary decision method based on the power plant speed governor digital mapping model according to claim 4 or 5, characterized in that: In the step of determining the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed: Constructing a line graph based on the grid frequency and the generator speed at each time point in the determination time period; Based on the slope of the line between every two adjacent time points in the line graph corresponding to the grid frequency and the generator speed, a first fluctuation trend vector and a second fluctuation trend vector are respectively constructed.

7. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 6 is characterized in that: The step of determining the fluctuation trend of the grid frequency or the generator speed in the determination time period based on the historical data of the grid frequency or the generator speed also includes: Calculate a third fluctuation trend vector symmetrical to the second fluctuation trend vector based on the second fluctuation trend vector; A total fluctuation trend vector is calculated based on the first fluctuation trend vector and the third fluctuation trend vector, and the total fluctuation trend vector is used as the fluctuation trend of the determination time period.

8. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 7 is characterized in that: In the step of comparing the fluctuation trend of the grid frequency or the generator speed with the load change trend in the determination time period based on a preset digital mapping model to determine whether a load shedding situation occurs: Constructing a line graph based on the load value at each time point in the determination time period, and constructing a load change vector based on the slope of the line connecting every two adjacent time points in the line graph; The total fluctuation trend vector and the load change vector corresponding to the fluctuation trend of the determination time period are input into the pre-trained digital mapping model to obtain the trend coincidence degree; Whether a load shedding situation occurs is determined based on the trend coincidence.

9. The speed governor auxiliary decision-making method based on the power plant speed governor digital mapping model according to claim 8 is characterized in that: In the step of determining whether a load shedding situation occurs based on the trend coincidence, if the trend coincidence is greater than a preset coincidence threshold, it is determined that a load shedding situation occurs.

10. A speed governor auxiliary decision system based on a power plant speed governor digital mapping model, characterized in that: The system includes a computer device, which includes a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method described in any one of claims 1 to 9.

Images